© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13400
    Prev
    Next
    INDEX
    Explanations

    the word "regardless", but it also activates upon words that represent a counterpoint, like "discounts" and "shakes"

    oai_token-act-pair · gemini-2.0-flash

    regardless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lean
    -0.91
     Roskov
    -0.85
    Lean
    -0.75
    LEAN
    -0.74
    lean
    -0.71
    tagHelperRunner
    -0.71
     HasFactory
    -0.67
     jScrollPane
    -0.66
     >=",
    -0.65
    ArgsConstructor
    -0.64
    POSITIVE LOGITS
    <bos>
    1.30
    erializer
    0.51
     duda
    0.45
    konomi
    0.44
    場合
    0.43
    zunehmen
    0.42
    AutoresizingMask
    0.42
     autonomie
    0.42
    日閲覧
    0.41
    댓글
    0.40
    Activations Density 1.189%

    No Known Activations